Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-32K
    6. 18104
    Prev
    Next
    INDEX
    Explanations

    punctuations and formatting errors in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whilst
    -0.36
     Whilst
    -0.34
    Whilst
    -0.27
    #
    -0.22
     amongst
    -0.19
     due
    -0.17
    .Disclaimer
    -0.16
    due
    -0.16
     unfortunate
    -0.16
    .Please
    -0.16
    POSITIVE LOGITS
    Officials
    0.22
    That
    0.22
    [np
    0.21
     Officials
    0.20
    But
    0.19
    FILE
    0.19
     That
    0.19
    Authorities
    0.18
    And
    0.17
    DATABASE
    0.17
    Activations Density 0.091%

    No Known Activations